SLIM-0.5B: Learning Action-Grounded Predictive Latents for Robot Manipulation

2026-08-10

AI Summary

This work addresses key limitations of existing vision-language-action (VLA) models—namely parameter redundancy, high computational cost, and the inclusion of semantically irrelevant information—in robotic continuous control. The authors propose SLIM, a self-supervised latent interaction model with only 0.5B parameters, which uniquely integrates action reconstruction with future latent prediction. By leveraging masked trajectory prediction, SLIM learns predictive latent representations grounded in actions, jointly modeling observations, actions, and their dynamic relationships. Built upon a hybrid Transformer backbone and eschewing pixel-level modeling, SLIM enables efficient language-conditioned action generation via flow matching. Notably, it achieves competitive or superior performance compared to large-scale VLA and world models in both simulation and real-world settings—without requiring additional embodied pretraining—while operating at lower latency, reduced memory footprint, and significantly smaller model size.

Abstract

Vision-language-action policies rely on large multimodal backbones to jointly perform perception, language conditioning, and action generation at every control step. Much of this capacity supports open-domain semantics, whereas continuous robot manipulation primarily requires compact representations of observations, actions, and the transitions induced by actions. Pixel-level world models provide another route, but predicting visual details irrelevant to control can be unnecessarily expensive. We propose SLIM (Self-supervised Latent Interaction Model), a compact 0.5B-parameter latent interaction policy. SLIM learns action-grounded predictive latents that capture both action-conditioned future transitions and the actions that explain observed changes. SLIM learns these representations through self-supervised masked trajectory prediction, combining action reconstruction with future-latent prediction. A compact Mixture-of-Transformers (MoT) backbone models interactions between observation latents and action tokens. The resulting policy is trained with flow matching for language-conditioned action generation. Across simulation benchmarks and real-world evaluation, SLIM matches or exceeds representative large-scale VLA and world-action-model baselines with fewer parameters, no additional embodied pretraining, lower inference latency, and substantially lower GPU memory usage.

Problem

• robot manipulation
• compact representation
• vision-language-action policies
• world models
• action-conditioned prediction

Innovation

• action-grounded latents
• self-supervised trajectory prediction
• Mixture-of-Transformers
• flow matching
• compact robot policy